language_parser.py 文件源码

def fetch_all_organizations(resume_text):
  organizations = set()
  tokenized_sentences = nltk.sent_tokenize(resume_text)

  # Custom grammar with NLTK
  # NP - Noun Phrase
  # NN - Noun
  # NNP - Proper Noun
  # V - Verb
  # JJ - Adjective

  # In a sentence that contains NN NNNP V NN NN JJ NN.
  # The noun-phrases fetched are:
  # NP: NN NNP
  # NP: NN NN
  # NP: NN

  # Ex, "Application Developer at Delta Force"
  # => ["Application Developer", "Delta Force"]

  grammar = r"""NP: {<NN|NNP>+}"""
  parser = nltk.RegexpParser(grammar)

  avoid_organizations = utilities.get_avoid_organizations()

  for sentence in tokenized_sentences:

    # tags all parts of speech in the tokenized sentences
    tagged_words = nltk.pos_tag(nltk.word_tokenize(sentence))

    # then chunks with customize grammar
    # np_chunks are instances of class nltk.tree.Tree
    np_chunks = parser.parse(tagged_words)
    noun_phrases = []

    for np_chunk in np_chunks:
      if isinstance(np_chunk, nltk.tree.Tree) and np_chunk.label() == 'NP':
        # if np_chunk is of grammer 'NP' then create a space seperated string of all leaves under the 'NP' tree
        noun_phrase = ""
        for (org, tag) in np_chunk.leaves():
          noun_phrase += org + ' '

        noun_phrases.append(noun_phrase.rstrip())

    # Using name entity chunker to get all the organizations
    chunks = nltk.ne_chunk(tagged_words)
    for chunk in chunks:
      if isinstance(chunk, nltk.tree.Tree) and chunk.label() == 'ORGANIZATION':
        (organization, tag) = chunk[0]

        # if organization is in the noun_phrase, it means that there is a high chance of noun_phrase containing the employer name
        # eg, Delta Force is added to organizations even if only Delta is recognized as an organization but Delta Force is a noun-phrase
        for noun_phrase in noun_phrases:
          if organization in noun_phrase and organization not in avoid_organizations:
            organizations.add(noun_phrase.capitalize())

  return organizations